{ "metadata": { "ParamSize": 578, "ParamBytes": 23532068352.0, "BitsPerParam": 15.446912771926858 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 2013757440, "records": [ { "name": "language_model.model.embed_tokens.weight", "shape": [ 262208, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2013757440, "byteOffset": 0 } ], "md5sum": "4c499998174d26e775acdee115b96e50" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.0.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "694f3ff9463cccf8ef11daba5f278dba" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.0.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "c9ba781388532b0adf5415e2adfea72c" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.0.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "76c172f512517d5820f5bca3c7266b1a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.0.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a7b43e2a50a84f771cde00bf840f1bf2" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.1.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "e170e1a3a77659c90bc5685619a49580" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.1.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "584e5cf70d4a84a21410219dc789e27b" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31520256, "records": [ { "name": "language_model.model.layers.0.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 0 }, { "name": "language_model.model.layers.0.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 7680 }, { "name": "language_model.model.layers.0.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 15360 }, { "name": "language_model.model.layers.0.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 23040 }, { "name": "language_model.model.layers.0.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 30720 }, { "name": "language_model.model.layers.0.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 31232 }, { "name": "language_model.model.layers.0.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15759872 }, { "name": "language_model.model.layers.0.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15760384 }, { "name": "language_model.model.layers.1.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31489024 }, { "name": "language_model.model.layers.1.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31496704 }, { "name": "language_model.model.layers.1.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31504384 }, { "name": "language_model.model.layers.1.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31512064 }, { "name": "language_model.model.layers.1.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31519744 } ], "md5sum": "f6d400d9fe31648e53241bc4c4f96280" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.1.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c3a0aca398130afa108e848a95799394" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.1.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b5602166c0c1e9ad407cc71af04fe4b8" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.2.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "70742158955d161f43740289e944df92" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.2.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "364deddc8693c8a8d7a6b31d7ec356a3" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.1.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.1.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.1.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.2.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.2.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.2.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.2.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.2.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "7b069fa06b296528625eeb68bb818815" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.2.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e36b17d85e71b5af120b1c7897cb66ec" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.2.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "7522636b929e1fd55a328ec01d52897b" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.3.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "22f0b9a1703faf514ccd32ed085e4fa6" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.3.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "553b1ff68246383c14427d7476281531" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.2.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.2.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.2.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.3.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.3.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.3.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.3.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.3.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "2cf1205656ccddad9ec9b524f1f90433" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.3.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "aa50b66ce22a21d2702f37f1261117be" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.3.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ce442f24cfab9dfeff749678d0ee85a4" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.4.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "5db405192b62c17eb379f28abc5b9496" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 31458304, "records": [ { "name": "language_model.model.layers.3.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.3.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.3.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.4.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31457792 } ], "md5sum": "c4f59dd3d1a2b0f22a91f9cf56a28638" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.4.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "24980e414afde5b5af6e146e99105d2b" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.4.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ef4f00ee83bf72171c7d31a12cc8d881" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.10.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "acd2fc1b14e8fa5fc3cd833378dd57f2" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.10.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "dd6b18c2ea294a5fe35147f656761f9d" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.4.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.4.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.4.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.10.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.10.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.10.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.10.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.10.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "423144725aead1dcb2be24317cb40a74" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.10.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "eb6a12c133ce56d8337ea05d7559845c" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.10.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "790bdd90ae6c3219e6f4f81f2d613cdf" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.11.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "d6efdcf8887277f524de6ae248f5d4ce" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.11.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "ca922e3df4769b57815863456a775b8f" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.10.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.10.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.10.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.11.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.11.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.11.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.11.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.11.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "ab06a7e74bf62bfb2b71924962cc89d2" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.11.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "f870745d099d6451c6172b7b6dbd00ea" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.11.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "24e1e299c77a5838174f4b3f0cd5bb76" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.12.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "a44a403b34519bc21d1abd2e298a5789" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.12.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "f68f098dfb37c6adf7c8aad0e9d938d8" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.11.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.11.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.11.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.12.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.12.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.12.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.12.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.12.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "1e4cee49278cc453ae6cd7f5df16e965" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.12.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "5e23cc2029b696319f806ab4667b7084" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.12.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "7ea9af01278ce41aa4bd7c0ea5e87897" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.13.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "369fc2e40553ab0e90846b2dd6c7eba6" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.13.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "57b34e2b75ffb5a6b46ceaf0845bc24e" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.12.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.12.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.12.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.13.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.13.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.13.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.13.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.13.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "3c5c8fdfd48d9a2b09598caed168b3d0" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.13.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "596c753a20b80a189d5a3d1f36bcb9b4" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.13.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "4b9d111afa0c328cbfd70b322295d079" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.14.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "a6414b86e20baab5638d59bce299f85f" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.14.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "7954186d59d8c8f12fa8beb7a0f52a5a" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.13.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.13.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.13.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.14.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.14.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.14.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.14.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.14.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "575cafd858759c2fe4a944543356e871" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.14.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0d03ab476d7af232ef1fadd84d605588" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.14.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "9e0dbd883bc73bf207f78d2e73a98b61" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.15.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "4fd6bc24e6d1761375c5ad06a7cb3f67" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 31458304, "records": [ { "name": "language_model.model.layers.14.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.14.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.14.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.15.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31457792 } ], "md5sum": "c66c0ec9b7fbbddd91f6bf6bf0d5da90" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.15.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "5b464e9180bba551e5d5bd39a9e978f4" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.15.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "1c50aaf4e00ad3cf5ca5349d1e1eb85c" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.4.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "79e9b50478c9ef14fd88d834c378c545" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.5.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "e38b3321bc997274d180bbbe6dfa537d" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.5.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "6cca383592456b47d18e1b7a84cf0af3" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 31519744, "records": [ { "name": "language_model.model.layers.15.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.15.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.15.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.4.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.4.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.4.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.4.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.5.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31488512 }, { "name": "language_model.model.layers.5.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31496192 }, { "name": "language_model.model.layers.5.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31503872 }, { "name": "language_model.model.layers.5.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31511552 }, { "name": "language_model.model.layers.5.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31519232 } ], "md5sum": "99f120feb645cdcccb7591c88b4738d9" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.5.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ee40302b14269e0f0bc8c62733df6095" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.5.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "da8a956820f7847582ceed34d590139f" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.6.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "dcc378f2685bf0f4f81875ee6ea827e8" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.6.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "f8fe829bd98e9be1a818e10d2d81512a" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.5.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.5.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.5.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.6.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.6.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.6.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.6.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.6.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "6c15c3e4a81f766a62c6275e53e2d090" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.6.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "f35c8fee25580bc5093912e9cb43b3ef" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.6.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e1c4c7e79daa04865ab0c4ee4d3cdf47" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.7.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "d200fe9315f2034662ab3e79e74ebb95" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.7.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "301b624c19b2d2c9740d07d41a2f2aa1" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.6.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.6.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.6.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.7.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.7.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.7.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.7.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.7.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "cab4ed44a9b70435fa91d25b72b8e5aa" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.7.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "5452d8db51930f54c59a88e348f85bff" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.7.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "98ebb87c35d296396908d449858aaa72" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.8.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "f87925d2e855c97b34b8dce249ee130e" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.8.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "88279cb0bd6f8d19aac5906577004aea" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.7.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.7.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.7.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.8.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.8.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.8.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.8.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.8.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "7eedb9faf4ba8eee58b186948197b610" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.8.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0d647c0d7b90d107e571545dbb487a72" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.8.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2e42da6fef4da6db0cf930e66c53cc2d" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.9.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "b4d844a0b51844ba9b3cb6a46b829388" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.9.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "d2b41216f228a503b04b028ef6139cc1" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.8.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.8.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.8.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.9.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.9.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.9.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.9.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.9.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "a00ab6441356e596086c831aa2234873" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.9.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2594f7a091cf97c28821532a2f315153" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.9.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "3c19c13aed5fa0b6b125b295ff2aec32" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.15.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "8f49a7a8441d4f69879c372350bb4e60" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.16.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "1fecfff19e4adebc60f2fb00b74512eb" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.16.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "80eff94bd799115ee7c5e2e87d604379" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 31519744, "records": [ { "name": "language_model.model.layers.9.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.9.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.9.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.15.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.15.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.15.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.15.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.16.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31488512 }, { "name": "language_model.model.layers.16.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31496192 }, { "name": "language_model.model.layers.16.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31503872 }, { "name": "language_model.model.layers.16.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31511552 }, { "name": "language_model.model.layers.16.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31519232 } ], "md5sum": "53f39149ca0b6b171cc9f528463fc31a" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.16.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "d0a341fa1da010e9461297a54afd4148" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.16.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a2f46ef59140bbe09be8443ebf093311" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.17.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "1ccbeaea6ac84329bee927a7c1106655" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.17.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "ebbd827a6e509e22b1802203c7baf077" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.16.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.16.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.16.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.17.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.17.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.17.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.17.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.17.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "b79ffb32093bd38c288c665a572e3a15" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.17.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "fb06b21d62ed1a1a2751615cf0871db8" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.17.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "7612e9e0389056c0589391aa17d054c0" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.18.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "4cf9361bb3c49c328f238f372be289f5" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.18.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "307b09045a86ab0ef2b579b28fc5938d" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.17.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.17.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.17.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.18.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.18.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.18.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.18.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.18.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "6775f1a87ea89f83b917953c0ec9f25a" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.18.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "dc0fb1c6dce6fe926f163f98aaedab8f" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.18.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "80e454b19cf584933b3d58c5b5623b13" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.19.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "45cc1d17aea287d4b18aa25616a85059" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.19.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "85c4175e464b679f3483c1dcf434807f" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.18.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.18.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.18.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.19.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.19.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.19.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.19.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.19.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "cf215ad5c20e124a7c0fb95d11a337d3" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.19.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b64dd8e2d883d7e3fc4e79948460025a" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.19.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "875f4cc45916d46d63017a667b603c4d" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.20.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "57f033e8be12863e1ad6d01cc572cbb8" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.20.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "be49e7c72ae1d30c7b890c4a5cfa2ca0" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.19.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.19.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.19.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.20.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.20.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.20.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.20.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.20.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "16af04cb18e076b27ebff9f058b298d1" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.20.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e82d26aa658d57e40ffe8dd25ae1e43f" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.20.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "4db4656214d8ecffc91193d476e29b21" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.21.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "2ad80c893651f4f6b6c14d6dc7d921d5" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.21.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "ebd45e05c922d5747a6795521a233c52" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.20.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.20.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.20.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.21.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.21.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.21.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.21.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.21.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "ce6798e96f92e42beb954f7f6ccea172" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.21.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "7159e57c3e9bd62d2a667e2a0ff66e8c" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.21.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "6eda996044e1b60ce46fdc17b98a2c75" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.22.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "0032ad7fdab5d2d02b660750c90568ec" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.22.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "fdd2f9ad43cf1058c5ab783d07bdb3c2" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.21.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.21.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.21.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.22.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.22.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.22.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.22.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.22.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "b383adedd475189097b793e010cb4ec0" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.22.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b8282bc5f8a8aca5619126a59c78bd81" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.22.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "49e9b13a059c31229c0c6b22d539ad79" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.23.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "e2a9ea24c18c5a42c7c6ca38de0bb9aa" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.23.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "7beb3a5a678485c8ea85e0d095945659" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.22.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.22.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.22.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.23.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.23.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.23.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.23.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.23.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "8580567f1a8ceea1689bd4241435fae2" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.23.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2c8f14e42346a0f93d5d9ef63e56a743" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.23.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "61706ec46dea1de3f402c1dd91c73b8b" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.24.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "458e377feb465728112394c06fe1e9a8" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.24.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "ffb8fd04095c44116a7e4f3a58e4f0eb" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.23.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.23.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.23.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.24.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.24.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.24.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.24.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.24.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "d4e70202d08daf6810f0810e29e23e11" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.24.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "06fa813656eaa50e124a679fe61a31d1" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.24.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "d3770a9bdce50be7e27b0096610503e8" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.25.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "2f84c106729a46c80bd24d3e18a4489b" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.25.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "887bc02d3c77ac9dcfc5db7c40286c6e" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.24.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.24.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.24.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.25.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.25.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.25.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.25.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.25.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "348b4d950517c213442960db958d789c" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.25.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "82784f75478e3b7878daa7f56fafe7e2" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.25.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "8a88155159f930744cf0a6213cc63f4b" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.26.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "2a5c11953a410ad252060e5221e5f558" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 31458304, "records": [ { "name": "language_model.model.layers.25.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.25.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.25.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.26.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31457792 } ], "md5sum": "5b8f8bdf8fa8f06c806f9b0f6964886a" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.26.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "08662e57c12012906d8c1353be42d53b" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.26.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0537e7db3f79c769afdbc912d2c467a6" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.26.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "65ebcae926f742a4f8cbe25722a347f0" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.27.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "4ad9e720671435d1572b725b4db1701b" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.27.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "60102c6c71496facea1d6dc200cb2eed" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 31519744, "records": [ { "name": "language_model.model.layers.26.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.26.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.26.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.26.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.26.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.26.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.26.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.27.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31488512 }, { "name": "language_model.model.layers.27.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31496192 }, { "name": "language_model.model.layers.27.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31503872 }, { "name": "language_model.model.layers.27.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31511552 }, { "name": "language_model.model.layers.27.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31519232 } ], "md5sum": "fe46cccf1f525bd06b868bbb48dd1949" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.27.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "cd47e987a0262d269a179f39a734bf3d" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.27.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "456fc4b476829c5f61514264b56a69f5" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.28.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "d8334b31a57f1302f4e61f0ff5149f3b" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.28.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "aa92e5ba0f0c37c6ddf43804d5094b3a" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.27.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.27.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.27.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.28.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.28.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.28.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.28.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.28.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "86988cb44f4e857d4569cc4f0e54c946" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.28.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "d7b3d05e0162d323df45f2ecf789e12f" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.28.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "947fd2591647ebdeddc4c2e02d5a49d9" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.29.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "c926fb2fb19d1f401702f1e9c380b3bd" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.29.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "2021dcefdd60d4364a41645275a294d8" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.28.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.28.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.28.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.29.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.29.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.29.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.29.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.29.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "9d4fcb7fc7e2dbb7fe0a51ca8f0e6d4a" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.29.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "9f34935e271a35043d2b1da2bee38a9f" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.29.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "8178e642b0e13b8657e5b969bebdb56f" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.30.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "cf505abc93502e74cc100207621619ae" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.30.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "6b26d41e5904912275882c9ca41fd2ea" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.29.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.29.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.29.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.30.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.30.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.30.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.30.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.30.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "d20f3c08b3815b1c997d505db181fe71" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.30.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0b0492df6a219cc8ec48bee6e944c281" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.30.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e8b05f03c13d24f2fa883e28bc6b9be7" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.31.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "e520f20c37dae0e2baec741607c79331" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.31.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "2e12e87630ae685757c1547754bd4e47" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.30.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.30.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.30.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.31.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.31.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.31.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.31.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.31.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "8fd9f89f9ff2fe97a51492900204ada0" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.31.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ba52fb904ba0f93c2ff1d1e8c9595630" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.31.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "1451755105d32edad24fd3df701eb417" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.32.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "debedec28e2bfd30967e10091f2cf587" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.32.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "d9afa3f69024fc4a2e28ecf923f73a4a" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.31.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.31.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.31.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.32.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.32.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.32.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.32.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.32.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "2d49ee3ad6056a10e831f53fa047d25f" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.32.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "26cdc833112f082297d718e3a96c4402" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.32.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "f2bd16587e48bb5de0ac39c2fb9e0ec6" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.33.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "caec172a1700c9484232dd6767b35303" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.33.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "a6a33033993a260b7fcf01c766743a1f" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.32.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.32.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.32.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.33.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.33.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.33.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.33.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.33.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "b2de5f3f85b7df09eae3f0e4d5ba0546" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.33.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a3b42166885635ecc45fef8990a9e7fc" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.33.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a21a11e73ed458ebbf6e9e4c518812df" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.34.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "f821b7b9f00542534ac11202d1b13bd3" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.34.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "49ba221f1edb441789041f93b592a48f" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.33.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.33.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.33.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.34.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.34.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.34.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.34.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.34.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "9d5674158b7ea7a5197a3e8150aaa5e7" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.34.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "44930876d535c0104667703dd1332d20" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.34.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b8724002851d65d74a27caf003dcaabf" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.35.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "91e43840f471b87090e9843a6a43ed67" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.35.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "a56733640ce98d910246aae26cf91c84" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.34.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.34.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.34.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.35.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.35.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.35.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.35.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.35.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "b0981a44f83d3902cff7098d0fa33066" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.35.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a383f3c19514cd990661aafa27f05c54" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.35.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0d21d8d7c65efbdedd32f5679414cfeb" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.36.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "7792a5bb823f631a0c1a18a603a77d37" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.36.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "6555bfff9d5ecdfaf210f7be2a207ed1" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.35.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.35.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.35.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.36.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.36.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.36.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.36.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.36.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "5a4d31f6c9021afa626cdb6a20af39fa" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.36.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "aa8f75620392a6d2256ddff8b5497025" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.36.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "bcb16c9fbd9e07eddbf221cd9c476227" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.37.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "eaae1d915f233e9c5f73fb31d39aa64e" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 31458304, "records": [ { "name": "language_model.model.layers.36.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.36.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.36.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.37.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31457792 } ], "md5sum": "3d1f92db6179a75e2097549181ef25c0" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.37.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0b85c9a21c8f9512d91a17113b090eac" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.37.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "63b279dd29b3b8fdb8d1332c7f76a580" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.37.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "9d209678ddd7d776b28647f1aee5e1b7" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.38.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "cacb2db113ede140a65248c311bc2385" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.38.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "ca28d02cb65061dad40a0447d162275b" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 31519744, "records": [ { "name": "language_model.model.layers.37.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.37.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.37.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.37.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.37.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.37.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.37.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.38.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31488512 }, { "name": "language_model.model.layers.38.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31496192 }, { "name": "language_model.model.layers.38.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31503872 }, { "name": "language_model.model.layers.38.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31511552 }, { "name": "language_model.model.layers.38.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31519232 } ], "md5sum": "2c133b469ad3666dc2ad21ce4d638a29" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.38.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "6c14ce0bd47cd010b65d8f410d197451" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.38.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b9e7c777fb4ff23a628a25ea19708c04" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.39.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "795409f1ef8a8e502e5823122a2dff57" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.39.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "8eb0ca2743bba502a162eacab0d2769a" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.38.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.38.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.38.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.39.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.39.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.39.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.39.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.39.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "f8e72d9fb460d2587a0e3b6f300c7acf" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.39.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "49403438a8bd1ea764a6b2b5b2ac6761" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.39.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2c35ab3dc9bab2b89f28e8d03683e1b4" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.40.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "fbe3d32b2f3e5f10bc4100d5e7001fbd" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.40.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "048cafa6600452fa0974be9d169115e0" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.39.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.39.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.39.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.40.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.40.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.40.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.40.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.40.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "5f6fbe96eade86c2c0fe821952dde81b" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.40.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "308c31e4dca11d1ab4ec91e471dde45d" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.40.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c446ba0e9242acb30e505f18832f73e0" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.41.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "e074d35b49411a1eb572eab62a5e107b" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.41.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "d8e8cdb926b89a725ce7b4f9e9712599" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.40.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.40.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.40.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.41.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.41.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.41.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.41.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.41.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "de933336fff0ffbd279cb1ec3dd6f3bc" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.41.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "462641e926a606e19549bd93eafbbb78" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.41.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "970fc4ef48313b0b62126d67839cc05d" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.42.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "b4f8de763f2480d2a4301041a25cafaf" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.42.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "c963e12118400cf1fff1099edd6e3d7e" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.41.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.41.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.41.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.42.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.42.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.42.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.42.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.42.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "d421b4dd211643a482b0ab7b9886fb91" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.42.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2e5949700c70beee6588558844aa024c" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.42.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "8905eb92b22bb9dea281a6c54af6001d" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.43.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "b875b36150f2168e82ce1f286d6c82ea" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.43.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "9e65e6e4f90be4968fc1700ed279862b" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.42.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.42.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.42.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.43.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.43.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.43.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.43.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.43.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "5c896ad5d24392c2a211923bce2f252d" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.43.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "fe82b8251c4d4e3b637cac3518e6bb0a" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.43.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "905c2643dcd61166d8fae89d553a373c" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.44.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "6315add6196417b8a413ca8a253b60bb" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.44.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "25b63ccf78001d30f5c4635767207970" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.43.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.43.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.43.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.44.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.44.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.44.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.44.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.44.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "c01a872b7ad08c34b39f9553da3cbab9" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.44.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "3ee04b3ad3500ddca1b78dd1542f00cd" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.44.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "37e2224fb46fa479bfb13e6642bba87a" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.45.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "95a3d2f0930a205a53ffb1c022106152" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.45.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "fc57bbe39f0e5128df14fbbf5bc7330c" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.44.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.44.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.44.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.45.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.45.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.45.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.45.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.45.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "9577ffdea541c6c5911c59516c1e517b" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.45.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "5fd632fc6ee79e29c417c0ae6f8304fd" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.45.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b1f54a43edcc15e9b174e63dd6fcb6a9" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.46.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "66a0c2cf1c575dd2910e19e9ee9afbd4" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.46.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "cdd51b2d27679f7576a978ba01c41790" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.45.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.45.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.45.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.46.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.46.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.46.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.46.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.46.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "64a0a7f54d8c7c2f129c718a3b135eea" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.46.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "f90c8810909c19ed67a0dbafcee62798" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.46.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ec2720b40f2921d384dc6d9836039e2b" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 117964800, "records": [ { "name": "language_model.model.layers.47.mlp.down_proj.weight", "shape": [ 3840, 15360 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 117964800, "byteOffset": 0 } ], "md5sum": "d4b4b68bf63ee1e6fac1bd3b15a58573" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 235929600, "records": [ { "name": "language_model.model.layers.47.mlp.gate_up_proj.weight", "shape": [ 30720, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 235929600, "byteOffset": 0 } ], "md5sum": "da5d8ce15fa25653090250fb2c06c995" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 31489024, "records": [ { "name": "language_model.model.layers.46.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.46.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.46.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.layers.47.input_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 }, { "name": "language_model.model.layers.47.post_attention_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31465472 }, { "name": "language_model.model.layers.47.post_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31473152 }, { "name": "language_model.model.layers.47.pre_feedforward_layernorm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31480832 }, { "name": "language_model.model.layers.47.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 31488512 } ], "md5sum": "c7f73551bfbd4c5643471523fb6ad6c7" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.47.self_attn.o_proj.weight", "shape": [ 3840, 4096 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "30e93a012e4361296c31c37379e8c32b" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "language_model.model.layers.47.self_attn.q_proj.weight", "shape": [ 4096, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a8f0b112fa6a8242dd9a6dd86120ff1e" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "language_model.model.layers.47.self_attn.k_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "language_model.model.layers.47.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15728640 }, { "name": "language_model.model.layers.47.self_attn.v_proj.weight", "shape": [ 2048, 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 15729152 }, { "name": "language_model.model.norm.weight", "shape": [ 3840 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 7680, "byteOffset": 31457792 } ], "md5sum": "8910f75da221aa71d0f7f5aa30a7ccbc" } ] }